ICLR

All Work

Natural language boosts LLM performance in coding, planning, and robotics
Natural language boosts LLM performance in coding, planning, and robotics
MIT News
A faster, better way to prevent an AI chatbot from giving toxic responses
A faster, better way to prevent an AI chatbot from giving toxic responses
MIT News
When computer vision works more like a brain, it sees more like people do
When computer vision works more like a brain, it sees more like people do
MIT McGovern Institute
TGRL: Teacher Guided Reinforcement Learning Algorithm for POMDPs
TGRL: Teacher Guided Reinforcement Learning Algorithm for POMDPs
 
Scaling audio-visual learning without labels
Scaling audio-visual learning without labels
MIT News
Helping robots handle fluids
Helping robots handle fluids
MIT News
Is conditional generative modeling all you need for decision-making?
Is conditional generative modeling all you need for decision-making?
 
Sampling with Mollified Interaction Energy Descent
Sampling with Mollified Interaction Energy Descent
 
Learning Proximal Operators to Discover Multiple Optima
Learning Proximal Operators to Discover Multiple Optima
 
AnyDA: Anytime Domain Adaptation
AnyDA: Anytime Domain Adaptation
 
Label-free Concept Bottleneck Models
Label-free Concept Bottleneck Models
 
Learning to Grow Pretrained Models for Efficient Transformer Training
Learning to Grow Pretrained Models for Efficient Transformer Training
 
PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification
PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification
 
Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning
Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning
 
Graph Neural Network-Inspired Kernels for Gaussian Processes in Semi-Supervised Learning
Graph Neural Network-Inspired Kernels for Gaussian Processes in Semi-Supervised Learning
 
FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation
FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation
 
Contrastive Audio-Visual Masked Autoencoder
Contrastive Audio-Visual Masked Autoencoder
 
ISAAC Newton: Input-based Approximate Curvature for Newton’s Method
ISAAC Newton: Input-based Approximate Curvature for Newton’s Method
 
SoftZoo: A Soft Robot Co-design Benchmark For Locomotion In Diverse Environments
SoftZoo: A Soft Robot Co-design Benchmark For Locomotion In Diverse Environments
 
DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physics
DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physics
 
Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness
Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness
 
What Is Missing in IRM Training and Evaluation? Challenges and Solutions
What Is Missing in IRM Training and Evaluation? Challenges and Solutions
 
Hyper-Decision Transformer for Efficient Online Policy Adaptation
Hyper-Decision Transformer for Efficient Online Policy Adaptation
 
TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization
TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization
 
Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks
Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks
 
A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity
A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity
 
Understanding new tasks through the lens of training data via exponential tilting
Understanding new tasks through the lens of training data via exponential tilting
 
Planning with Large Language Models for Code Generation
Planning with Large Language Models for Code Generation
 
Temperature Schedules for self-supervised contrastive methods on long-tail data
Temperature Schedules for self-supervised contrastive methods on long-tail data
 
Learning to grow machine-learning models
Learning to grow machine-learning models
MIT News
Adversarial Support Alignment
Adversarial Support Alignment
 
Data-Efficient Graph Grammar Learning for Molecular Generation
Data-Efficient Graph Grammar Learning for Molecular Generation
 
Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations
Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations
 
Can an Image Classifier Suffice For Action Recognition?
Can an Image Classifier Suffice For Action Recognition?
 
RegionViT: Regional-to-Local Attention for Vision Transformers
RegionViT: Regional-to-Local Attention for Vision Transformers
 
AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning
AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning
 
Bi-linear Value Networks for Multi-goal Reinforcement Learning
Bi-linear Value Networks for Multi-goal Reinforcement Learning
 
Overcoming The Spectral Bias of Neural Value Approximation
Overcoming The Spectral Bias of Neural Value Approximation
 
Neural Parameter Allocation Search
Neural Parameter Allocation Search
 
Extending the WILDS Benchmark for Unsupervised Adaptation
Extending the WILDS Benchmark for Unsupervised Adaptation
 
Network Augmentation for Tiny Deep Learning
Network Augmentation for Tiny Deep Learning
 
Multi-Critic Actor Learning: Teaching RL Policies to Act with Style
Multi-Critic Actor Learning: Teaching RL Policies to Act with Style
 
ComPhy: Compositional Physical Reasoning of Objects and Events from Videos
ComPhy: Compositional Physical Reasoning of Objects and Events from Videos
 
How unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis
How unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis
 
Optimizer Amalgamation
Optimizer Amalgamation
 
How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective
How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective
 
RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation
RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation
 
Topological Experience Replay
Topological Experience Replay
 
Linking Emergent and Natural Languages via Corpus Transfer
Linking Emergent and Natural Languages via Corpus Transfer
 
Monotonic Differentiable Sorting Networks
Monotonic Differentiable Sorting Networks
 
Contact Points Discovery for Soft-Body Manipulations with Differentiable Physics
Contact Points Discovery for Soft-Body Manipulations with Differentiable Physics
 
Controlling Directions Orthogonal to a Classifier
Controlling Directions Orthogonal to a Classifier
 
DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Tools
DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Tools
 
Natural Language Descriptions of Deep Visual Features
Natural Language Descriptions of Deep Visual Features
 
Generating new molecules with graph grammar
Generating new molecules with graph grammar
MIT News
Solving the challenges of robotic pizza-making
Solving the challenges of robotic pizza-making
MIT News
Better learning through ‘complex dough-manipulation’
Better learning through ‘complex dough-manipulation’
Tech Crunch
Reverse Engineering of Imperceptible Adversarial Image Perturbations
Reverse Engineering of Imperceptible Adversarial Image Perturbations
 
Using artificial intelligence to find anomalies hiding in massive datasets
Using artificial intelligence to find anomalies hiding in massive datasets
MIT News
FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations
FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations
 
Decentralized Learning for Overparameterized Problems: A Multi-Agent Kernel Approximation Approach
Decentralized Learning for Overparameterized Problems: A Multi-Agent Kernel Approximation Approach
 
Long Live the Lottery: The Existence of Winning Tickets in Lifelong Learning
Long Live the Lottery: The Existence of Winning Tickets in Lifelong Learning
 
Nano-Material Configuration Design with Deep Surrogate Langevin Dynamics
Nano-Material Configuration Design with Deep Surrogate Langevin Dynamics
 
Lite Transformer with Long-Short Range Attention
Lite Transformer with Long-Short Range Attention
 
Robust Overfitting may be mitigated by properly learned smoothening
Robust Overfitting may be mitigated by properly learned smoothening
 
On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
 
Generating Adversarial Computer Programs using Optimized Obfuscations
Generating Adversarial Computer Programs using Optimized Obfuscations
 
PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics
PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics
 
Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning
Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning
 
Learning Task Decomposition with Ordered Memory Policy Network
Learning Task Decomposition with Ordered Memory Policy Network
 
SenSeI: Sensitive Set Invariance for Enforcing Individual Fairness
SenSeI: Sensitive Set Invariance for Enforcing Individual Fairness
 
Individually Fair Gradient Boosting
Individually Fair Gradient Boosting
 
Individually Fair Ranking
Individually Fair Ranking
 
Statistical inference for individual fairness
Statistical inference for individual fairness
 
Learning-based Support Estimation In Sublinear Time
Learning-based Support Estimation In Sublinear Time
 
AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition
AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition
 
VA-RED^2: Video Adaptive Redundancy Reduction
VA-RED^2: Video Adaptive Redundancy Reduction
 
Large Associative Memory Problem in Neurobiology and Machine Learning
Large Associative Memory Problem in Neurobiology and Machine Learning
 
Can a Fruit Fly Learn Word Embeddings?
Can a Fruit Fly Learn Word Embeddings?
 
This hybrid AI system can understand causality in controlled environments
This hybrid AI system can understand causality in controlled environments
TheNextWeb
SenSR: the first practical algorithm for individual fairness
SenSR: the first practical algorithm for individual fairness
 
Why Gradient Clipping accelerates training for neural networks
Why Gradient Clipping accelerates training for neural networks
 
CLEVRER: The first video dataset for neuro-symbolic reasoning
CLEVRER: The first video dataset for neuro-symbolic reasoning
 
Fast and efficient black-box testing for AI cybersecurity
Fast and efficient black-box testing for AI cybersecurity
 
Learning to learn with distributional signatures for text data
Learning to learn with distributional signatures for text data
 
Layer-wise federated learning with FedMA
Layer-wise federated learning with FedMA
 
Learning Rate Rewinding for elegant neural network pruning
Learning Rate Rewinding for elegant neural network pruning
 
Implementation Matters in Deep RL: A Case Study on PPO and TRPO
Implementation Matters in Deep RL: A Case Study on PPO and TRPO
 
Once for All: Train One Network and Specialize it for Efficient Deployment
Once for All: Train One Network and Specialize it for Efficient Deployment
 
Deep Audio Priors Emerge From Harmonic Convolutional Networks
Deep Audio Priors Emerge From Harmonic Convolutional Networks
 
A Closer Look at Deep Policy Gradients
A Closer Look at Deep Policy Gradients